SOTAVerified

Text-To-Speech Synthesis

Text-To-Speech Synthesis is a machine learning task that involves converting written text into spoken words. The goal is to generate synthetic speech that sounds natural and resembles human speech as closely as possible.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 332 papers

TitleStatusHype
Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersCode7
ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-SpeechCode6
PaddleSpeech: An Easy-to-Use All-in-One Speech ToolkitCode6
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task LearningCode5
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language ModelingCode5
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow MatchingCode4
Enhancing Suno's Bark Text-to-Speech Model: Addressing Limitations Through Meta's Encodec and Pre-Trained HubertCode4
MoonCast: High-Quality Zero-Shot Podcast GenerationCode3
Matcha-TTS: A fast TTS architecture with conditional flow matchingCode3
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-SpeechCode3
Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesisCode2
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and SynthesisCode2
Sample-Efficient Diffusion for Text-To-Speech SynthesisCode2
EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-SpeechCode2
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency ModelsCode2
Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody ModellingCode2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPTCode2
FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech CodecCode2
A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous SpeechCode2
Towards Building Text-To-Speech Systems for the Next Billion UsersCode2
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech SynthesisCode2
GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-SpeechCode2
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level QualityCode2
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech SynthesisCode2
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier TransformCode2
Generative Modeling for Low Dimensional Speech Attributes with Neural Spline FlowsCode2
PortaSpeech: Portable and High-Quality Generative Text-to-SpeechCode2
DiffSinger: Singing Voice Synthesis via Shallow Diffusion MechanismCode2
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramCode2
FastSpeech: Fast, Robust and Controllable Text to SpeechCode2
FastSpeech: Fast,Robustand Controllable Text-to-SpeechCode2
Neural Speech Synthesis with Transformer NetworkCode2
Efficient Neural Audio SynthesisCode2
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsCode1
UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal PromptsCode1
KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech SynthesisCode1
Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechCode1
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer LearningCode1
ArTST: Arabic Text and Speech TransformerCode1
QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation LearningCode1
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech TranslationCode1
Multilingual Text-to-Speech Synthesis for Turkic Languages Using TransliterationCode1
Imaginary Voice: Face-styled Diffusion Model for Text-to-SpeechCode1
RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech SynthesisCode1
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis DatasetCode1
OverFlow: Putting flows on top of neural transducers for better TTSCode1
Accented Text-to-Speech Synthesis with a Conditional Variational AutoencoderCode1
MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied BaselineCode1
Automatic Prosody Annotation with Pre-Trained Text-Speech ModelCode1
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech RecognitionCode1
Show:102550
← PrevPage 1 of 7Next →
All datasetsLJSpeech20000 utterancesCMUDict 0.7bHUI speech corpusThorsten voice 21.02 neutralTrinity Speech-Gesture Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NaturalSpeechAudio Quality MOS4.56—Unverified
2VITSAudio Quality MOS4.43—Unverified
3Grad-TTS + HiFiGAN (1000 steps)Audio Quality MOS4.37—Unverified
4FastSpeech 2 + HiFiGANAudio Quality MOS4.34—Unverified
5Glow-TTS + HiFiGANAudio Quality MOS4.34—Unverified
6FastSpeech 2 + HiFiGANAudio Quality MOS4.32—Unverified
7FastDiff (4 steps)Audio Quality MOS4.28—Unverified
8FastDiff-TTSAudio Quality MOS4.03—Unverified
9Transformer TTS (Mel + WaveGlow)Audio Quality MOS3.88—Unverified
10FastSpeech (Mel + WaveGlow)Audio Quality MOS3.84—Unverified
#ModelMetricClaimedVerifiedStatus
1Mia10-keyword Speech Commands dataset16—Unverified
#ModelMetricClaimedVerifiedStatus
1Token-Level Ensemble DistillationPhoneme Error Rate4.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.74—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Match-TTSGMOS3.7—Unverified